Embedding Space Explorer

robert@barcik.training

Word embeddings represent words as points in a high-dimensional space, where semantically similar words are positioned close together. This 2D visualization shows how relationships between words are captured as geometric directions. For example, the vector from "man" to "king" is roughly the same as "woman" to "queen" — enabling arithmetic like king − man + woman ≈ queen. Click on any word to explore its neighbors, or try the vector arithmetic panel.

Filter:

Selected Word

Click a word on the plot to inspect it.

How Vector Arithmetic Works

Subtraction captures a relationship: king − man extracts a direction representing the "royalty concept."

Addition applies that relationship: adding the "royalty direction" to woman lands near queen.

Analogy: "king is to man as queen is to woman" — the arrow from man→king is the same direction as woman→queen. Try it below!

Vector Arithmetic

− +

Legend

AI transparency

This demo is a scripted, self-contained browser simulation. Nothing you type is sent to an AI model and no live AI system runs behind it, even where it plays one. Its code and copy were built with generative AI (Anthropic’s Claude) and reviewed by Robert Barcik, who is responsible for what is published (LearningDoe s.r.o.). Disclosed in the spirit of Article 50 of the EU AI Act.